arXiv research

Active seriation recovers item order from noisy pairwise similarity measurements.

We describe a seriation algorithm for ranking a set of items given pairwise comparisons between these items. Intuitively, the algorithm assigns similar rankings to items that compare similarly with all others. It does so by constructing a similarity matrix from pairwise comparisons, using seriation methods to reorder t…

Unified optimization framework for matrix seriation.

New methods rank players using covariates and comparisons, outperforming existing algorithms.

Given a matrix the seriation problem consists in permuting its rows in such way that all its columns have the same shape, for example, they are monotone increasing. We propose a statistical approach to this problem where the matrix of interest is observed with noise and study the corresponding minimax rate of estimatio…

Estimates latent positions in 1D torus from noisy pairwise affinities.

New method uses almost orthonormal bases to prove low-degree lower bounds in complex statistical models.

New algorithm optimizes matrix reordering for noisy disordered matrices.

cGAP visualizes high-dimensional categorical data with interpretable geometric structure.

cGAP visualizes high-dimensional categorical data with interpretable geometric structure.

Many activation functions have been proposed in the past, but selecting an adequate one requires trial and error. We propose a new methodology of designing activation functions within a neural network at each layer. We call this technique an "activation ensemble" because it allows the use of multiple activation functio…

This paper studies activation sparsity in large language models, finding key trends and implications.

Activity recognition from sensor data deals with various challenges, such as overlapping activities, activity labeling, and activity detection. Although each challenge in the field of recognition has great importance, the most important one refers to online activity recognition. The present study tries to use online hi…

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the activation, and the weights capture the scale. Here we propose to train the netw…

BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.

Evolutionary algorithms improve neural network performance by discovering better activation functions.

Active learning method balances bias and variance under class imbalance.

New method learns neural network activation functions from data.

Study active learning of PTFs with derivative access.

Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples giv…

Bayesian adaptive designs can be biased by active learning, especially with misspecified models.

Derives time-averaged active inference from control principles.

RAN model recognizes multiple activities from unlabeled sensor data.

A new indicator measures project risk from activity durations.

Hidden Markov Models detect hand gestures from wearable sEMG signals.

Active testing reduces label costs for efficient model evaluation.

Survey of trainable activation functions in neural networks.

This paper analyzes and improves active learning techniques for real-world projects.

Study active nematic forces on curved surfaces, revealing new coupling mechanisms.

This paper provides an overview of activation functions in neural networks.

Bayesian active learning method improved for censored regression data.

DUNs improve active learning by dynamically adjusting model complexity.

Large deviation principle for deep neural networks with ReLU activation.

TransFall uses transfer learning to improve activity recognition from mobile sensors.

Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by setting them to be identity functions randomly during training time. During testing, …

EmbraceNet fusion model for multi-sensor activity recognition.

New proof shows neural networks can memorize training data with high accuracy.

We consider active learning of deep neural networks. Most active learning works in this context have focused on studying effective querying mechanisms and assumed that an appropriate network architecture is a priori known for the problem at hand. We challenge this assumption and propose a novel active strategy whereby …

Data-aware activation function customization reduces neural network error.

In the last few years there has been a growing interest in Human Activity Recognition~(HAR) topic. Sensor-based HAR approaches, in particular, has been gaining more popularity owing to their privacy preserving nature. Furthermore, due to the widespread accessibility of the internet, a broad range of streaming-based app…

Active learning selects inputs for GPSSM to learn latent states.

Active learning is an important technique to reduce the number of labeled examples in supervised learning. Active learning for binary classification has been well addressed in machine learning. However, active learning of the reject option classifier remains unaddressed. In this paper, we propose novel algorithms for a…

This paper explores adaptive neural activation in RNNs for better learning.

DAL uses disentanglement for automatic labeling in GAN-based active learning.

Active-memory mechanisms can replace self-attention in Transformers, but optimal results often require both.

There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation ability of deep neural networks with a broad class of activation functi…

Unified study of active learning for deep neural networks.

Deep learning models outperform classical methods in forecasting neural activity.